The AVL 9180 Electrolyte Analyzer is intended to be used for the measurement of sodium, potassium, chloride, ionized calcium and lithium in whole blood, serum or plasma, urine, dialysate solutions, or QC materials as appropriate by minimally trained personnel qualified to perform and to report these values in a clinical laboratory setting. These analytes are commonly used in the diagnosis and management of patients with a broad range of renal, metabolic and cardiovascular disorders and, as such, have come to be among those which are considered by the American Association of Clinical Chemistry to have the potential of being life threatening if left uncontrolled.
Device Story
Microprocessor-based electrolyte analyzer; uses ion-selective electrodes (ISE) for direct potentiometric measurement of sodium, potassium, chloride, ionized calcium, and lithium. Input: whole blood, serum, plasma, urine, dialysate, or QC materials via syringe, capillary, or microsampler. Operation: automatic sample aspiration, processing, and analysis. Output: results displayed on screen and printed via built-in thermal printer. Used in clinical laboratory settings by trained personnel. Provides quantitative electrolyte values to assist clinicians in diagnosing and managing renal, metabolic, and cardiovascular disorders. Benefits: rapid, automated electrolyte assessment for potentially life-threatening conditions.
Clinical Evidence
Three clinical field tests compared the AVL 9180 against predicate devices (AVL 983, 984, 985, IL 943, Kodak Ektachem XR700) using remnant patient specimens (whole blood, serum, urine). Results showed no significant difference in mean values (P<0.05). Correlation coefficients were generally >0.94 across all analytes. Non-clinical testing included precision studies (20 days, 2 runs/day) and linearity studies using NIST-traceable aqueous standards and patient serum/urine samples, confirming performance within manufacturer claims.
Technological Characteristics
Microprocessor-based instrument; ion-selective electrode (ISE) sensing principle; direct potentiometry. Configurations: Na+/K+/Ca2+, Na+/K+/Cl-, Na+/K+/Li+, Na+/K+, Na+/Li+, or Li+. Connectivity: RS 232 C interface (ASCII/ASTM). Power: 100-240 VAC. Dimensions: 13.2 x 12.4 x 12.0 inches. Weight: 13 lb. Safety: Class I, IP 20, continuous operation. Calibration: 2-point automatic every 4 hours, 1-point automatic per measurement.
Indications for Use
Indicated for patients requiring measurement of sodium, potassium, chloride, ionized calcium, or lithium in whole blood, serum, plasma, urine, or dialysate to assist in the diagnosis and management of renal, metabolic, and cardiovascular disorders.
Regulatory Classification
Identification
A calcium test system is a device intended to measure the total calcium level in serum. Calcium measurements are used in the diagnosis and treatment of parathyroid disease, a variety of bone diseases, chronic renal disease and tetany (intermittent muscular contractions or spasms).
I.L. Model 943 Flame Emission Photometer (not specified)
Labconco Digital Chloridometer (not specified)
Reference Devices
AVL 9130 Electrolyte Analyzer
AVL 9140 Electrolyte Analyzer
KODAK Ektachem XR700
Submission Summary (Full Text)
{0}
K961458
AVL
# 510(k) Summary
JUN 12 1996
## (a) (1) Submitter's name, address
AVL Scientific Corporation
33 Mansell Court
Roswell, GA 30076
**Contact Person**
Randy Byrd
Quality Assurance Manager
(770) 587-4040 x 631
**Date of preparation of this summary:**
10 April 1996
## (2) Device trade or proprietary name:
AVL 9180 Electrolyte Analyzer
**Device common or usual name or classification name**
Ion-specific electrolyte analyzer for sodium, potassium and chloride or ionized calcium or lithium.
| Product Nomenclature | Classification Number | Class | Panel |
| --- | --- | --- | --- |
| ELECTRODE, ION-SPECIFIC, CALCIUM | 75 JFP | II | CHEMISTRY |
| ELECTRODE, ION-SPECIFIC, CHLORIDE | 75 CGZ | II | CHEMISTRY |
| FLAME PHOTOMETER, LITHIUM | 75 JIH | II | TOXICOLOGY |
| ELECTRODE, ION-SPECIFIC, POTASSIUM | 75 CEM | II | CHEMISTRY |
| ELECTRODE, ION-SPECIFIC, SODIUM | 75 JGS | II | CHEMISTRY |
## (3) Substantial Equivalence
The AVL 9180 is an improved design of our ISE electrolyte analyzer line to provide the user an ability to only exchange electrodes to change configuration between sodium, potassium and chloride to sodium, potassium and ionized calcium or sodium, potassium and lithium. The 9180, configured for sodium, potassium and chloride is equivalent to the AVL 983 Na/K/Cl Analyzer [K861087]; for sodium, potassium and ionized calcium, to the AVL 984 Na/K/iCa Analyzer [K862819] and; for sodium, potassium and lithium to the AVL 985 Na/K/Li Analyzer [K870657]. Additionally, for sodium, potassium and lithium the AVL 9180 is substantially equivalent to the I.L. Model 943 Flame Emission Photometer and for chloride, to the Labconco Digital Chloridometer.
## (4) Description of the new device
The AVL 9180 Electrolyte Analyzer is a microprocessor-based instrument using ion-selective electrodes for the measurement of sodium, potassium, chloride, ionized calcium and lithium. The user is able to select any one of the measurement modes: whole blood, serum, urine, standard, QC material, acetate or bicarbonate dialysate, depending on the sample type to be analyzed. The analyzer automatically processes the sample through the necessary steps, then prints and displays the results.
In the blood, serum and QC measuring modes, the results for sodium and potassium are reported by default as flame photometry equivalent; chloride, ionized calcium and lithium are reported as ISE direct potentiometric values. The urine mode allows for the measurement of prediluted urine samples for sodium, potassium and chloride. The acetate, bicarbonate and standard modes allow for the measurement of aqueous standards and dialysate solutions and reports as ISE direct potentiometric values.
B
{1}
510(k) Summary
AVL 9180 Electrolyte Analyzer
## (5) Intended use of the device.
The AVL 9180 Electrolyte Analyzer is intended to be used for the measurement of sodium, potassium, chloride, ionized calcium and lithium in whole blood, serum or plasma, urine, dialysate solutions, or QC materials as appropriate by minimally trained personnel qualified to perform and to report these values in a clinical laboratory setting. These analytes are commonly used in the diagnosis and management of patients with a broad range of renal, metabolic and cardiovascular disorders and, as such, have come to be among those which are considered by the American Association of Clinical Chemistry to have the potential of being life threatening if left uncontrolled.
## (6) Technological characteristics of the device.
### Principles of Measurement
The principles of measurement used in the AVL 9180 Electrolyte Analyzer are identical to those principles existing in the electrolyte analyzers to which substantial equivalence is claimed in paragraph (a)(3) above.
### Calibration
The AVL 9180 contains software which permits operation in one of six parameter configurations: Na⁺/K⁺/Ca²⁺, Na⁺/K⁺/Cl⁻, Na⁺/K⁺/Li⁺, Na⁺/K⁺, Na⁺/Li⁺ or Li⁺. A 2-point calibration is performed automatically every 4 hours in READY mode, and a 1-point calibration is performed automatically with each measurement.
### Technical Specifications
#### Measured Values
| Parameter | Range | Display Resolution | units |
| --- | --- | --- | --- |
| whole blood, serum, plasma, dialysate and aqueous solutions | | | |
| Sodium | 40 - 205 | 0.1 | mmol/L |
| Potassium | 1.5 - 15 | 0.1 or 0.01 | mmol/L |
| Chloride | 50 - 200 | 0 or 0.1 | mmol/L |
| ionized Calcium | 0.2 - 5.0 | 0.01 or 0.001 | mmol/L |
| Lithium | 0.1 - 6.0 | 0.01 or 0.001 | mmol/L |
| urine | | | |
| Sodium | 1-300 | 0 | mmol/L |
| Potassium | 4.5 - 120 | 0.1 | mmol/L |
| | (60 - 120 with additional dilution) | | |
| Chloride | 1 - 300 | 0 | mmol/L |
Page 2
(19)
{2}
510(k) Summary
AVL 9180 Electrolyte Analyzer
## Operating Conditions
- Minimum Sample Size: 95 µL
- Sample Type: heparinized whole blood, serum, plasma, urine aqueous standards and acetate or bicarbonate dialysate solutions
- Sample Application: syringe, capillary or AVL Microsampler, collection tube or sample cup
- Sample Input: automatic aspiration
- Ambient Temperature: +15 - +32 °C (59 - 90 °F)
- Relative Humidity: 5% to 95% (non-condensing)
- Type of Measurement: direct potentiometry
## Data Management
- Printout: Built-in thermal printer
- Interface: RS 232 C with selectable baud rate
- Format: 8 bits, no parity, 1 stop bit, ASCII or ASTM (bi-directional)
## Electrical Supply
- Voltage: 100 - 240 VAC (50-60 Hz)
- Power Consumption: 1.4 VA max., 375 max.
## Dimensions and Weight
- Height x width x depth: 13.2 x 12.4 x 12.0 inches (33.5 x 31.5 x 29.5 cm)
- Weight: 13 lb. (6 kg)
## Classifications
- Safety category: I
- Device type: B (according to ÖVE-MG/EN 60601-1, IEC 601-1)
- Mode of operation: continuous operation
- Protection classification: IP 20
- Explosion protection: the device is not designed for operation in explosive environments
- Approvals: CSA, IEC 1010 (TÜV/GS), CE
## (b) (1) Summary of nonclinical tests submitted with the premarket notification for the device. Precision
Typical Within-Run (Swr) Between-Day (Sdd) and Total (St) Precision is determined from 2 runs per day with 2 replicates per run for 20 days on two model AVL 9180 analyzers in each of its three main configurations using samples of each of the specimen types suitable for measurement on the 9180.
20
{3}
510(k) Summary
AVL 9180 Electrolyte Analyzer
# Linearity in Aqueous Standard Solutions
Aqueous linearity standards were gravimetrically prepared from N.I.S.T. traceable salts and measured on each of six AVL 9180 instruments, two of each configuration: Na/K/Cl, Na/K/iCa and Na/K/Li.
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 0.99993 | 0.0128 | 0.99995 | 0.666 | 51 - 196 | 300 |
| Potassium | 0.99838 | 0.0119 | 0.99919 | 0.194 | 2.0 - 12.6 | 300 |
| Chloride | 0.97556 | -0.1775 | 0.99994 | 0.674 | 56 - 194 | 100 |
| ionized Calcium | 1.01552 | -0.0078 | 0.99980 | 0.037 | 0.4 - 3.3 | 100 |
| Lithium | 0.99850 | 0.0087 | 0.99985 | 0.038 | 0.3 - 5.3 | 100 |
# Linearity in Serum
Linearity in serum was established with the analysis of two specimen sets in non-clinical tests: commercially prepared serum linearity standards for sodium, chloride and potassium with normal protein content, and a group of random patient serum samples. All samples were analyzed in pairs on each of two of AVL 9180 instruments in each configuration: Na/K/Cl, Na/K/iCa and Na/K/Li. and in pairs on each of several instrument types for comparison to various methods:
vs. Flame Absorbance Emission Spectroscopy (IL 943 Flame Photometer)
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 0.9617 | 5.83 | 0.9908 | 2.04 | 104 - 178 | 50 |
| normalized to Na=140 | | 0.47 | | | | |
| Potassium | 1.0249 | 0.015 | 0.9991 | 0.075 | 1.8 - 11.5 | 50 |
| normalized to K=4.0 | | 0.11 | | | | |
| Lithium | 0.9803 | 0.011 | 0.9822 | 0.028 | 0.11 - 0.71 | 15 |
vs. ISE Direct Potentiometry (AVL 983, AVL 984, AVL 985 Electrolyte Analyzers)
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 0.9895 | -6.35 | 0.9992 | 0.61 | 110 - 186 | 50 |
| Potassium | 1.0223 | -0.25 | 0.9996 | 0.05 | 2.0 - 11.6 | 50 |
| Chloride | 0.9631 | -1.01 | 0.9995 | 0.51 | 70 - 152 | 50 |
| ionized Calcium | 0.8898 | 0.107 | 0.9960 | 0.021 | 0.67 - 1.66 | 50 |
| Lithium | 0.9923 | 0.008 | 0.9985 | 0.010 | 0.11 - 0.71 | 15 |
vs. ISE Direct Potentiometry with flame correlation (AVL 9130, AVL 9140 Electrolyte Analyzers)
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 0.9856 | -2.02 | 0.9856 | 1.21 | 104 - 179 | 50 |
| Potassium | 0.9992 | 0.02 | 0.9994 | 0.05 | 1.9 - 11.8 | 50 |
| Chloride | 1.0026 | -5.31 | 0.9989 | 0.73 | 70 - 152 | 50 |
| ionized Calcium | 1.0023 | 0.040 | 0.9954 | 0.022 | 0.62 - 1.54 | 50 |
Page 4
{4}
510(k) Summary
AVL 9180 Electrolyte Analyzer
# Linearity in Urine
Linearity in urine was evaluated with the analysis of random patient urine specimens on two, AVL 9810 Electrolyte Analyzers in the Na/K/Cl configuration and, in duplicate on two AVL 983 Na/K/Cl Electrolyte Analyzers for sodium, potassium and chloride; on a IL 943 Flame Photometer for sodium and potassium; and on a Labconco Digital Chloridometer for chloride.
vs. direct ISE (AVL 983) in urine
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 1.0173 | -7.4382 | 0.9973 | 5.55 | 4 - 262 | 56 |
| Potassium | 1.0312 | -0.1539 | 0.9976 | 2.24 | 6 - 147 | 56 |
| Chloride | 0.9817 | 2.4630 | 0.9972 | 5.64 | 16 - 299 | 56 |
vs. flame absorbance emission spectroscopy (IL 943 Flame Photometer) in urine
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 0.9173 | 0.5627 | 0.9901 | 10.64 | 7 - 285 | 56 |
| Potassium | 1.0312 | -0.1539 | 0.9976 | 2.24 | 6 - 147 | 56 |
vs. chloridometry (Labconco Digital) Chloridometer in urine
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Chloride | 0.9817 | 2.4630 | 0.9972 | 5.64 | 16 - 299 | 56 |
## (b) (2)
Summary of clinical tests submitted with the premarket notification for the device. Three field tests were conducted to demonstrate the correlation of the AVL 9180 to legally marketed predicate devices in a clinical setting, operated by personnel trained to perform and report these analyses. Specimens analyzed in these tests were remnant from patient specimens collected for routing analysis on existing instrumentation.
In all evaluations, there was no difference in mean values ($P<0.05$) obtained on measurement by the AVL 9180 and the predicate device. The table below provides data representative of that collected in these field tests.
vs. thin-film slide; KODAK Ektachem XR700 in serum
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 1.0459 | -6.6196 | 0.9495 | 1.67 | 125 - 158 | 103 |
| Potassium | 1.0895 | -0.2740 | 0.9873 | 0.10 | 2.8 - 6.2 | 103 |
| Chloride | 0.9505 | 6.2577 | 0.9762 | 1.32 | 85 - 125 | 103 |
Page 5
{5}
510(k) Summary
AVL 9180 Electrolyte Analyzer
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 0.9208 | 10.1267 | 0.9485 | 1.19 | 112 - 142 | 102 |
| Potassium | 0.9820 | 0.0879 | 0.9933 | 0.16 | 3.2 - 12.3 | 102 |
| Chloride | 0.8346 | 13.3572 | 0.9674 | 1.45 | 83 - 118 | 102 |
| ionized Calcium | 1.0020 | 0.0800 | 0.9783 | 0.02 | 0.78 - 1.37 | 102 |
vs. direct ISE (AVL 984 Electrolyte Analyzer) in whole blood
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Sodium | 0.9918 | -6.4874 | 0.9682 | 0.94 | 123 - 149 | 102 |
| Potassium | 0.9671 | -0.0380 | 0.9974 | 0.10 | 3.3 - 12.8 | 102 |
| ionized Calcium | 0.9491 | 0.0374 | 0.9825 | 0.02 | 0.87 - 1.47 | 102 |
vs. direct ISE (AVL 985 Electrolyte Analyzer) in whole blood
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Lithium | 1.0799 | -0.0203 | 0.9986 | 0.03 | 0.19 - 3.34 | 104 |
vs. flame absorbance emission spectroscopy (IL 943 Flame Photometer) in serum
| Parameter | Slope | Intercept | Correlation Coefficient | Sy*x | Range | n |
| --- | --- | --- | --- | --- | --- | --- |
| Lithium | 0.9720 | 0.0163 | 0.9957 | 0.02 | 0.23 - 1.13 | 15 |
(b) (3) Conclusions drawn from the clinical and nonclinical trials.
Analysis of the comparative measurement presented in the 510(k) for this device, together with the linearity and precision data collected during these clinical and nonclinical trials demonstrates that the AVL 9180 in any of the available configurations for measurement, is safe and effective. There is no significant difference in the measurement values obtained on whole blood, serum or urine with the AVL 9180 and those obtained with predicate devices in this study and the precision and linearity demonstrated both in clinical and non clinical trials is within the manufacturers claims and expectations.
Page 6
23
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.